Triple
T21600077
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Andalasia |
E533011
|
entity |
| Predicate | languageInFilm |
P52200
|
FINISHED |
| Object | English |
—
|
LITERAL FINISHED |
How this triple was built (2 steps)
Every LLM step that produced this triple, in pipeline order — named-entity classification, the disambiguation choices (the exact options shown, with the pick highlighted), and the generated description. The batch + timestamp of each is in the Provenance table below.
NER
Named-entity recognition
gpt-5-mini
Instruction
Given a phrase, classify it is english named entity (e.g., persons, organizations, works of art) in Latin script, or not (e.g., literals, dates, URLs, verbose phrases). For disambiguation, the statement where the phrase occurs as object is also given. Please return a JSON object with `phrase` (string, the phrase being analyzed) and `is_ne` (boolean, indicating whether the phrase is a Named Entity).
Input
Phrase: English | Statement: [Andalasia, languageInFilm, English]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: languageInFilm Context triple: [Andalasia, languageInFilm, English]
-
A.
filmedInLanguage
Indicates that a film or video work was originally recorded using a particular spoken or signed language.
-
B.
filmLanguageFormat
Indicates the specific language and presentation format (e.g., dubbed, subtitled, original audio) in which a film is released or available.
-
C.
languageSpokenOnScreen
chosen
Indicates that a particular language is used in spoken dialogue or audible communication within an on-screen work (such as a film, show, or video).
-
D.
areSpokenIn
Indicates that a particular language is used as a spoken means of communication within a specified region, community, or context.
-
E.
primaryFilmingLanguage
Indicates the main language in which a film or audiovisual work was originally filmed or recorded.
- F. None of above.
Provenance (3 batches)
The batch behind each pipeline step, in order, with when it ran. Timestamps are batch-level — stages were processed in waves, so the object chain (NER → NED1 → NEDg → NED2) reads in order, but predicate / elicitation batches can sit in a different wave.
| Step | Stage | Batch ID | Status | When |
|---|---|---|---|---|
| creating | Elicitation | batch_69e0c46364608190a337dc8720dc2a35 |
completed | April 16, 2026, 11:13 a.m. |
| NER | Named-entity recognition | batch_69ef17e12fdc8190ab6125ea8d294717 |
completed | April 27, 2026, 8:01 a.m. |
| PD | Predicate disambiguation | batch_69e632109d048190b4ac3f14fe48d1a0 |
completed | April 20, 2026, 2:02 p.m. |
Created at: April 16, 2026, 6:32 p.m.